Data and Factors
Kerry Back
Basics
- Price and volume
- Company financials
- Analyst forecasts
- Earnings surprises
- Dividend announcements
Data on positions and trades
- Corporate insiders
- Short interest
- Quarterly fund filings
- Retail order flow (buy and sell)
Macroeconomic data
- Federal Reserve Economic Data (FRED)
- Energy Information Administration (EIA)
- World Bank, …
Sentiment data
- Scrape social media or buy/scrape news
- Extract mentions of tickers
- Use machine-learning NLP (natural language processing) to classify as positive, negative, or neutral
Other data
- Images
- Satellite and drone imagery
- Warehouse truck activity, cars in parking lots, …
- Use machine learning/AI to analyze images
- Search engine traffic
- Phone location, …
Monthly returns and characteristics
- We’ll use monthly data 2000-2021.
- Monthly returns
- 100+ stock characteristics known at the beginning of each month from
- past prices
- company financials
- analyst forecasts
- earnings announcements
- Mimic trading monthly
- Form portfolio at beginning of month
- Observe returns and changes in characteristics
- Form new portfolio, …
- Data is on a SQL server at CloudClusters.net
- Variable definitions
Factor investing
Factors are stock characteristics such that
- stocks that share characteristics tend to move together
- characteristics predict average returns
Value, momentum, profitability, investment rate, volatility, accruals, …
Overview of machine learning
- What do we want to predict?
- Return?
- Return minus average return?
- Rank of return (1, 2, 3, …)?
- Whether return will be in top, middle, bottom? Or deciles?
- What predictors do we want to use?
- What model do we want to use?
Some models
- Forests
- Random forests
- Boosting
- Neural networks
- Linear regression and variants